Maclory / Deep-Iterative-Collaboration

Pytorch implementation of Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation (CVPR 2020)
MIT License
295 stars 63 forks source link

How to make Visual Result in the paper. #46

Open choieq opened 3 years ago

choieq commented 3 years ago

Hi,

I'm graduate student studying about FSR.

May i ask you how to make Visual Result(visual comparison with SOTA FSRs) in the paper and this repository?

Because in my case, it shows different(weird) results depending on how i crop face in the image. I tried cropping while maintaining face aspect ratio. But still the result is weird.

The result here in CelebA dataset tightly cropped by RetinaFace .. Second figure is padding image to maintain aspect ratio. image

image

And this is result by using dataset presented by this repository. image

Can you explained that?